Optimizing Machine Learning Performance

Por: Coursera . en: , ,


This course synthesizes everything your have learned in the applied machine learning specialization. You will now walk through a complete machine learning project to prepare a machine learning maintenance roadmap. You will understand and analyze how to deal with changing data. You will also be able to identify and interpret potential unintended effects in your project. You will understand and define procedures to operationalize and maintain your applied machine learning model. By the end of this course you will have all the tools and understanding you need to confidently roll out a machine learning project and prepare to optimize it in your business context.

To be successful, you should have at least beginner-level background in Python programming (e.g., be able to read and code trace existing code, be comfortable with conditionals, loops, variables, lists, dictionaries and arrays). You should have a basic understanding of linear algebra (vector notation) and statistics (probability distributions and mean/median/mode).

This is the final course of the Applied Machine Learning Specialization brought to you by Coursera and the Alberta Machine Intelligence Institute (Amii).


Machine Learning Strategy
-This week we'll present tools for understanding the overall strategy your business needs in order to see the best returns on ML investment. From understanding the current status to navigating ownership and setting up a team, this week is about understanding applied machine learning in a successful business context.

Responsible Machine Learning
-This week we'll talk about the broader context of machine learning: how as developers we have responsibilities regarding how our technology will be used. Using case studies and existing frameworks we'll give you the tools to figure out your own ethical approach to realize the best outcomes while deploying machine learning in the real world.

Machine Learning in Production & Planning
-An important aspect of machine learning in the real world is considering how your machine learning models are integrated with existing systems, and what effect they have on your operations. This week we'll review things you should consider as you turn QuAMs and machine learning models into operational tools.

Care and Feeding of your Machine Learning System
-Work doesn't end just because your model is deployed! In our final week we'll go over all the things you need to consider in the context of an actual working system.